{
  "best_metric": 0.5190518498420715,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.0034402683409305926,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 6.880536681861185e-05,
      "grad_norm": 28.9600887298584,
      "learning_rate": 0.0001,
      "loss": 11.6662,
      "step": 1
    },
    {
      "epoch": 6.880536681861185e-05,
      "eval_loss": 12.078635215759277,
      "eval_runtime": 2139.5291,
      "eval_samples_per_second": 2.86,
      "eval_steps_per_second": 1.43,
      "step": 1
    },
    {
      "epoch": 0.0001376107336372237,
      "grad_norm": 29.409589767456055,
      "learning_rate": 0.0002,
      "loss": 11.6662,
      "step": 2
    },
    {
      "epoch": 0.00020641610045583555,
      "grad_norm": 18.24087905883789,
      "learning_rate": 0.00019978589232386035,
      "loss": 10.4243,
      "step": 3
    },
    {
      "epoch": 0.0002752214672744474,
      "grad_norm": 16.715696334838867,
      "learning_rate": 0.00019914448613738106,
      "loss": 6.4008,
      "step": 4
    },
    {
      "epoch": 0.00034402683409305926,
      "grad_norm": 17.853330612182617,
      "learning_rate": 0.00019807852804032305,
      "loss": 5.9125,
      "step": 5
    },
    {
      "epoch": 0.0004128322009116711,
      "grad_norm": 29.21288299560547,
      "learning_rate": 0.00019659258262890683,
      "loss": 6.844,
      "step": 6
    },
    {
      "epoch": 0.00048163756773028296,
      "grad_norm": 25.7408447265625,
      "learning_rate": 0.0001946930129495106,
      "loss": 3.7796,
      "step": 7
    },
    {
      "epoch": 0.0005504429345488948,
      "grad_norm": 25.737831115722656,
      "learning_rate": 0.0001923879532511287,
      "loss": 2.1666,
      "step": 8
    },
    {
      "epoch": 0.0006192483013675067,
      "grad_norm": 29.130735397338867,
      "learning_rate": 0.00018968727415326884,
      "loss": 1.3214,
      "step": 9
    },
    {
      "epoch": 0.0006880536681861185,
      "grad_norm": 29.522249221801758,
      "learning_rate": 0.00018660254037844388,
      "loss": 0.5459,
      "step": 10
    },
    {
      "epoch": 0.0007568590350047304,
      "grad_norm": 9.462636947631836,
      "learning_rate": 0.00018314696123025454,
      "loss": 0.2734,
      "step": 11
    },
    {
      "epoch": 0.0008256644018233422,
      "grad_norm": 0.6041041612625122,
      "learning_rate": 0.00017933533402912354,
      "loss": 0.006,
      "step": 12
    },
    {
      "epoch": 0.0008944697686419541,
      "grad_norm": 6.003550052642822,
      "learning_rate": 0.00017518398074789775,
      "loss": 0.9383,
      "step": 13
    },
    {
      "epoch": 0.0009632751354605659,
      "grad_norm": 0.08332598209381104,
      "learning_rate": 0.00017071067811865476,
      "loss": 0.0026,
      "step": 14
    },
    {
      "epoch": 0.0010320805022791778,
      "grad_norm": 0.11768299341201782,
      "learning_rate": 0.00016593458151000688,
      "loss": 0.0049,
      "step": 15
    },
    {
      "epoch": 0.0011008858690977896,
      "grad_norm": 1.0236197710037231,
      "learning_rate": 0.00016087614290087208,
      "loss": 0.1537,
      "step": 16
    },
    {
      "epoch": 0.0011696912359164015,
      "grad_norm": 0.2157546728849411,
      "learning_rate": 0.00015555702330196023,
      "loss": 0.0989,
      "step": 17
    },
    {
      "epoch": 0.0012384966027350133,
      "grad_norm": 4.32232666015625,
      "learning_rate": 0.00015000000000000001,
      "loss": 0.1766,
      "step": 18
    },
    {
      "epoch": 0.0013073019695536252,
      "grad_norm": 0.3158111870288849,
      "learning_rate": 0.00014422886902190014,
      "loss": 0.1451,
      "step": 19
    },
    {
      "epoch": 0.001376107336372237,
      "grad_norm": 1.1058377027511597,
      "learning_rate": 0.000138268343236509,
      "loss": 0.1624,
      "step": 20
    },
    {
      "epoch": 0.0014449127031908489,
      "grad_norm": 0.4658142328262329,
      "learning_rate": 0.00013214394653031616,
      "loss": 0.1471,
      "step": 21
    },
    {
      "epoch": 0.0015137180700094607,
      "grad_norm": 0.9202958345413208,
      "learning_rate": 0.00012588190451025207,
      "loss": 0.152,
      "step": 22
    },
    {
      "epoch": 0.0015825234368280726,
      "grad_norm": 1.466764211654663,
      "learning_rate": 0.00011950903220161285,
      "loss": 0.1262,
      "step": 23
    },
    {
      "epoch": 0.0016513288036466844,
      "grad_norm": 0.9088215231895447,
      "learning_rate": 0.00011305261922200519,
      "loss": 0.0405,
      "step": 24
    },
    {
      "epoch": 0.0017201341704652963,
      "grad_norm": 0.22232256829738617,
      "learning_rate": 0.00010654031292301432,
      "loss": 0.0104,
      "step": 25
    },
    {
      "epoch": 0.0017201341704652963,
      "eval_loss": 0.5998122692108154,
      "eval_runtime": 2142.0619,
      "eval_samples_per_second": 2.857,
      "eval_steps_per_second": 1.429,
      "step": 25
    },
    {
      "epoch": 0.0017889395372839081,
      "grad_norm": 1.5337985754013062,
      "learning_rate": 0.0001,
      "loss": 0.3045,
      "step": 26
    },
    {
      "epoch": 0.00185774490410252,
      "grad_norm": 1.4691545963287354,
      "learning_rate": 9.345968707698569e-05,
      "loss": 0.3119,
      "step": 27
    },
    {
      "epoch": 0.0019265502709211318,
      "grad_norm": 1.3081196546554565,
      "learning_rate": 8.694738077799488e-05,
      "loss": 0.2755,
      "step": 28
    },
    {
      "epoch": 0.0019953556377397437,
      "grad_norm": 1.1037979125976562,
      "learning_rate": 8.049096779838719e-05,
      "loss": 0.2116,
      "step": 29
    },
    {
      "epoch": 0.0020641610045583555,
      "grad_norm": 0.4469464421272278,
      "learning_rate": 7.411809548974792e-05,
      "loss": 0.1618,
      "step": 30
    },
    {
      "epoch": 0.0021329663713769674,
      "grad_norm": 4.526829242706299,
      "learning_rate": 6.785605346968386e-05,
      "loss": 0.2283,
      "step": 31
    },
    {
      "epoch": 0.0022017717381955793,
      "grad_norm": 3.505985736846924,
      "learning_rate": 6.173165676349103e-05,
      "loss": 0.2295,
      "step": 32
    },
    {
      "epoch": 0.002270577105014191,
      "grad_norm": 1.414526343345642,
      "learning_rate": 5.577113097809989e-05,
      "loss": 0.1727,
      "step": 33
    },
    {
      "epoch": 0.002339382471832803,
      "grad_norm": 0.5344605445861816,
      "learning_rate": 5.000000000000002e-05,
      "loss": 0.1778,
      "step": 34
    },
    {
      "epoch": 0.002408187838651415,
      "grad_norm": 0.6289926767349243,
      "learning_rate": 4.444297669803981e-05,
      "loss": 0.1095,
      "step": 35
    },
    {
      "epoch": 0.0024769932054700267,
      "grad_norm": 0.9150691628456116,
      "learning_rate": 3.9123857099127936e-05,
      "loss": 0.0482,
      "step": 36
    },
    {
      "epoch": 0.0025457985722886385,
      "grad_norm": 0.17626339197158813,
      "learning_rate": 3.406541848999312e-05,
      "loss": 0.0967,
      "step": 37
    },
    {
      "epoch": 0.0026146039391072504,
      "grad_norm": 0.4345886707305908,
      "learning_rate": 2.9289321881345254e-05,
      "loss": 0.0217,
      "step": 38
    },
    {
      "epoch": 0.002683409305925862,
      "grad_norm": 1.1442958116531372,
      "learning_rate": 2.4816019252102273e-05,
      "loss": 0.1938,
      "step": 39
    },
    {
      "epoch": 0.002752214672744474,
      "grad_norm": 1.16999351978302,
      "learning_rate": 2.0664665970876496e-05,
      "loss": 0.2015,
      "step": 40
    },
    {
      "epoch": 0.002821020039563086,
      "grad_norm": 0.31168338656425476,
      "learning_rate": 1.6853038769745467e-05,
      "loss": 0.0151,
      "step": 41
    },
    {
      "epoch": 0.0028898254063816978,
      "grad_norm": 0.39355605840682983,
      "learning_rate": 1.339745962155613e-05,
      "loss": 0.1057,
      "step": 42
    },
    {
      "epoch": 0.0029586307732003096,
      "grad_norm": 0.34757792949676514,
      "learning_rate": 1.0312725846731175e-05,
      "loss": 0.0168,
      "step": 43
    },
    {
      "epoch": 0.0030274361400189215,
      "grad_norm": 1.0999107360839844,
      "learning_rate": 7.612046748871327e-06,
      "loss": 0.1886,
      "step": 44
    },
    {
      "epoch": 0.0030962415068375333,
      "grad_norm": 0.3693877160549164,
      "learning_rate": 5.306987050489442e-06,
      "loss": 0.0992,
      "step": 45
    },
    {
      "epoch": 0.003165046873656145,
      "grad_norm": 0.39368072152137756,
      "learning_rate": 3.40741737109318e-06,
      "loss": 0.0189,
      "step": 46
    },
    {
      "epoch": 0.003233852240474757,
      "grad_norm": 1.0401899814605713,
      "learning_rate": 1.921471959676957e-06,
      "loss": 0.1791,
      "step": 47
    },
    {
      "epoch": 0.003302657607293369,
      "grad_norm": 0.31976115703582764,
      "learning_rate": 8.555138626189618e-07,
      "loss": 0.0979,
      "step": 48
    },
    {
      "epoch": 0.0033714629741119807,
      "grad_norm": 1.008750081062317,
      "learning_rate": 2.141076761396521e-07,
      "loss": 0.1768,
      "step": 49
    },
    {
      "epoch": 0.0034402683409305926,
      "grad_norm": 1.0031132698059082,
      "learning_rate": 0.0,
      "loss": 0.1768,
      "step": 50
    },
    {
      "epoch": 0.0034402683409305926,
      "eval_loss": 0.5190518498420715,
      "eval_runtime": 2142.0667,
      "eval_samples_per_second": 2.857,
      "eval_steps_per_second": 1.429,
      "step": 50
    }
  ],
  "logging_steps": 1,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 25,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 1,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 7.41887283560448e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}